Pith. sign in

REVIEW

Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2208.12885 v1 pith:KOTBL5IY submitted 2022-08-26 cs.CV cs.AIcs.LGeess.IVeess.SP

classification cs.CVcs.AIcs.LGeess.IVeess.SP
keywords domainenergy-basedmodeltargetadaptationclassificationdeepminimization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, thus easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective. It can be achieved via a simple additional regularization or an energy-based loss. This framework allows us to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. The convergence property and its connection with classification expectation minimization are investigated. We deliver extensive experiments on the most popular and large-scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

Discussion (0). Sign in to comment.

Pith tools